Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 297 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.3889. Min Range: -4.3889

Max Act: 4.3889. Min Act: -0.0001

Data Index: 416448 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 4.3889. Min Range: -4.3889

Max Act: 3.6232. Min Act: -0.0000

Data Index: 1319284 (C4 (Web Text))

Max Activating Token Index: 449

Text #2

Max Range: 4.3889. Min Range: -4.3889

Max Act: 3.2164. Min Act: -0.0000

Data Index: 700768 (C4 (Web Text))

Max Activating Token Index: 436

Text #3

Max Range: 4.3889. Min Range: -4.3889

Max Act: 3.3752. Min Act: -0.0000

Data Index: 101873 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 4.3889. Min Range: -4.3889

Max Act: 3.5952. Min Act: -0.0000

Data Index: 220048 (C4 (Web Text))

Max Activating Token Index: 677

Text #5

Max Range: 4.3889. Min Range: -4.3889

Max Act: 3.5359. Min Act: -0.0001

Data Index: 1252673 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 4.3889. Min Range: -4.3889

Max Act: 3.6802. Min Act: -0.0000

Data Index: 366048 (C4 (Web Text))

Max Activating Token Index: 797

Text #7

Max Range: 4.3889. Min Range: -4.3889

Max Act: 3.2336. Min Act: -0.0000

Data Index: 887142 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 4.3889. Min Range: -4.3889

Max Act: 3.1779. Min Act: -0.0001

Data Index: 783415 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 4.3889. Min Range: -4.3889

Max Act: 3.3014. Min Act: -0.0001

Data Index: 683082 (C4 (Web Text))

Max Activating Token Index: 97

Text #10

Max Range: 4.3889. Min Range: -4.3889

Max Act: 2.8562. Min Act: -0.0000

Data Index: 1142491 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 4.3889. Min Range: -4.3889

Max Act: 3.5320. Min Act: -0.0001

Data Index: 160770 (C4 (Web Text))

Max Activating Token Index: 553

Text #12

Max Range: 4.3889. Min Range: -4.3889

Max Act: 3.2382. Min Act: -0.0000

Data Index: 985725 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 4.3889. Min Range: -4.3889

Max Act: 3.1969. Min Act: -0.0001

Data Index: 687013 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 4.3889. Min Range: -4.3889

Max Act: 2.9648. Min Act: -0.0001

Data Index: 367937 (C4 (Web Text))

Max Activating Token Index: 781

Text #15

Max Range: 4.3889. Min Range: -4.3889

Max Act: 3.5050. Min Act: -0.0001

Data Index: 1155883 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 4.3889. Min Range: -4.3889

Max Act: 3.3081. Min Act: -0.0000

Data Index: 398218 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 4.3889. Min Range: -4.3889

Max Act: 3.3673. Min Act: -0.0001

Data Index: 1341042 (C4 (Web Text))

Max Activating Token Index: 685

Text #18

Max Range: 4.3889. Min Range: -4.3889

Max Act: 3.0797. Min Act: -0.0000

Data Index: 426838 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 4.3889. Min Range: -4.3889

Max Act: 3.1032. Min Act: -0.0000

Data Index: 1327712 (C4 (Web Text))

Max Activating Token Index: 612